1998
DOI: 10.21236/ada366982
|View full text |Cite
|
Sign up to set email alerts
|

Active Blobs

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
47
0

Year Published

1998
1998
2016
2016

Publication Types

Select...
3
3
1

Relationship

2
5

Authors

Journals

citations
Cited by 56 publications
(47 citation statements)
references
References 0 publications
0
47
0
Order By: Relevance
“…In our case the templates are computed in the texture map plane. A similar approach has been successfully used in [5,9,19].…”
Section: Formulationmentioning
confidence: 99%
See 1 more Smart Citation
“…In our case the templates are computed in the texture map plane. A similar approach has been successfully used in [5,9,19].…”
Section: Formulationmentioning
confidence: 99%
“…Once we know the initial position of the model we can generate a collection of warping templates from the reference texture [9,13,19]. Given a parameter displacement matrix N a = n 1 n 2 : : : n D ] we compute the warping templates matrix B = b 1 b 2 : : : b K ] with columns: b k = T 0 ; ;(I 0 a 0 + n k ) (2) where I 0 is the initial frame of the sequence, n k is the parameter displacement vector for the k th difference vector (warping template), and a 0 is the initial warping parameter vector (i.e., the initial position and orientation of the cylinder).…”
Section: Model Initializationmentioning
confidence: 99%
“…Furthermore, correlation-based methods are not well-suited to tracking moving objects that undergo scaling, rotation, or nonrigid deformation, since tracking is accomplished via correlation with a translating template. Larger deformations can be accomodated if the problem is posed in terms of deformable image registration [2,23]. In particular, La Cascia, et al [6], use this approach to register a texture-mapped polygonal model of a person's head with an incoming video sequence.…”
Section: Related Workmentioning
confidence: 99%
“…We model the region using the active blob formulation [23]. Tracking of the voodoo doll's deformation is modeled in terms of a deformable, triangular mesh that captures object shape plus a color texture map that captures object appearance.…”
Section: Approachmentioning
confidence: 99%
See 1 more Smart Citation